dtwclust-methods: Methods for `dtwclust`

Description

Methods associated with dtwclust-class objects.

Usage

"show"(object)
"update"(object, ..., evaluate = TRUE)
"update"(object, ..., evaluate = TRUE)
"predict"(object, newdata = NULL, ...)
"predict"(object, newdata = NULL, ...)
"plot"(x, y, ..., clus = seq_len(x@k), labs.arg = NULL, data = NULL, time = NULL, plot = TRUE, type = NULL)
"plot"(x, y, ..., clus = seq_len(x@k), labs.arg = NULL, data = NULL, time = NULL, plot = TRUE, type = NULL)

Arguments

object, x

An object of class dtwclust-class as returned by dtwclust.

...

For plot, further arguments to pass to geom_line for the plotting of the cluster centroids, or to plot.hclust. See details. For update, any supported argument. Otherwise ignored.

evaluate

Logical. Defaults to TRUE and evaluates the updated call, which will result in a new dtwclust object. Otherwise, it returns the unevaluated call.

newdata

New data to be assigned to a cluster. It can take any of the supported formats of dtwclust. Note that for multivariate series, this means that it must be a list of matrices, even if the list has only one element.

Ignored.

clus

A numeric vector indicating which clusters to plot.

labs.arg

Arguments to change the title and/or axis labels. See labs for more information

data

Optionally, the data in the same format as it was provided to dtwclust.

time

Optional values for the time axis. If series have different lengths, provide the time values of the longest series.

plot

Logical flag. You can set this to FALSE in case you want to save the ggplot object without printing anything to screen

type

What to plot. NULL means default. See details.

Value

The plot method returns a gg object (or NULL for dendrogram plot) invisibly.

Plotting

The plot method uses the ggplot2 plotting system (see ggplot). The default depends on whether a hierarchical method was used or not. In those cases, the dendrogram is plotted by default; you can pass any extra parameters to plot.hclust via .... Otherwise, the function plots the time series of each cluster along with the obtained centroid. The default values for cluster centroids are: linetype = "dashed", size = 1.5, colour = "black", alpha = 0.5. You can change this by means of .... You can choose what to plot with the type parameter. Possible options are:

"dendrogram": Only available for hierarchical clustering.
"series": Plot the time series divided into clusters without including centroids.
"centroids": Plot the obtained centroids only.
"sc": Plot both series and centroids

The flag save.data should be set to TRUE when running dtwclust to be able to use this. Optionally, you can manually provide the data in the data parameter. If created, the function returns the gg object invisibly, in case you want to modify it to your liking. You might want to look at ggplot_build if that's the case. If you want to free the scale of the X axis, you can do the following: plot(object, plot = FALSE) + facet_wrap(~cl, scales = "free")

Details

Supported generics from the flexclust package are: randIndex and clusterSim.

All generics from package clue are also supported in order to use its functions.

Show method displays basic information from the clustering results.

The update method takes the original function call, replaces any provided argument and optionally evaluates the call again. Use evaluate = FALSE if you want to get the unevaluated call.

The predict generic can take the usual newdata argument and it returns the cluster(s) to which the data belongs; if NULL, it simply returns the obtained cluster indices. It preprocesses the data with the corresponding function if available.